-
公开(公告)号：US20180247194A1
公开(公告)日：2018-08-30
申请号：US15903605
申请日：2018-02-23
Applicant: STMICROELECTRONICS S.r.l.
Inventor： Emanuele PLEBANI , Danilo Pietro PAU
Abstract: A classification device receives sensor data from a set of sensors and generates, using a context classifier having a set of classifier model parameters, a set of raw predictions based on the received sensor data. Temporal filtering and heuristic filtering are applied to the raw predictions, producing filtered predictions. A prediction error is generated from the filtered predictions, and model parameters of the set of classifier model parameters are updated based on said prediction error. The classification device may be a wearable device.
-
2.发明申请公开(公告)号：US20250053807A1
公开(公告)日：2025-02-13
申请号：US18779807
申请日：2024-07-22
Inventor： Danilo Pietro PAU , Surinder Pal SINGH , Fabrizio Maria Aymone
Abstract: The present disclosure relates to a method of training a neural network using a circuit comprising a memory and a processing device, an exemplary method comprising: performing a first forward inference pass through the neural network based on input features to generate first activations, and generating an error based on a target value, and storing the error to the memory; and performing, for each layer of the neural network: a modulated forward inference pass; before, during or after the modulated forward inference pass, a second forward inference pass based on the input features to regenerate one or more first activations; and updating one or more weights in the neural network based on the modulated activations and the one or more regenerated first activations.
-
公开(公告)号：US20180322393A1
公开(公告)日：2018-11-08
申请号：US15965803
申请日：2018-04-27
Applicant: STMICROELECTRONICS S.R.L.
Inventor： Danilo Pietro PAU , Marco PIASTRA , Luca CARCANO
CPC classification number: G06N3/088 , G06F3/011 , G06F3/017 , G06N3/0445 , G06N3/0481
Abstract: A neural network includes one layer of neurons including neurons having neuron connections to neurons in the layer and input connections to a network input. The neuron connections and the input connections have respective neuron connection weights and input connection weights. The neurons have neuron responses set by an activation function with activation values and include activation function computing circuits configured for computing current activation values of the activation function as a function of previous activation values of the activation function and current network input values.
-
公开(公告)号：US20180089586A1
公开(公告)日：2018-03-29
申请号：US15280463
申请日：2016-09-29
Applicant: STMicroelectronics S.r.l.
Inventor： Danilo Pietro PAU , Emanuele PLEBANI
IPC: G06N99/00 , A61B5/0205 , A61B5/11 , A61B5/00 , G06N3/04
CPC classification number: G06N20/00 , A61B5/0205 , A61B5/02055 , A61B5/02438 , A61B5/1118 , A61B5/7264 , G06K9/00342 , G06K9/6273 , G06N3/04
Abstract: Human activities are classified based on activity-related data and an activity-classification model trained using a classification-equalized training data set. A classification signal is generated based on the classifications. The classification-equalized training data set, may, for example, includes a first class having a first sequence length and a number of samples N, and one or more additional classes each having a respective sequence length tj and a respective number of samples Nj determined based on the number of samples N of the first class. For example, a respective sequence length tj and a respective number of samples Nj which satisfy: (i) Nj>N, for sequence length tj; and (ii) Nj
-
Patent Agency Ranking
公开(公告)号：US20230068500A1
公开(公告)日：2023-03-02
申请号：US17461457
申请日：2021-08-30
Inventor： Danilo Pietro PAU , Alessandro CREMONESI
Abstract: A device includes a memory and processing circuitry coupled to the memory. The processing circuitry, in operation, generates an indication of a predicted difference in a direction of arrival (DoA) of a signal using a trained autoregressive model. A predicted indication of a DoA of the signal is generated based on a previous indication of the DoA of the signal and the indication of the predicted difference in the DoA of the signal. The processing circuitry actuates or controls an antenna array based on predicted indications of the DoA of the signal.
-
6.发明申请公开(公告)号：US20210026695A1
公开(公告)日：2021-01-28
申请号：US16924091
申请日：2020-07-08
Applicant: STMicroelectronics S.r.l.
Inventor： Emanuele PLEBANI , Mirko FALCHETTO , Danilo Pietro PAU
Abstract: Methods, microprocessors, and systems are provided for implementing an artificial neural network. Data buffers in virtual memory are coupled to respective processing layers in the artificial neural network. An ordered visiting sequence of layers of the artificial neural network is obtained. A virtual memory allocation schedule is produced as a function of the ordered visiting sequence of layers of the artificial neural network, the schedule including a set of instructions for memory allocation and deallocation operations applicable to the data buffers. A physical memory configuration dataset is computed as a function of the virtual memory allocation schedule for the artificial neural network, the dataset including sizes and addresses of physical memory locations for the artificial neural network.
-
公开(公告)号：US20200160102A1
公开(公告)日：2020-05-21
申请号：US16752347
申请日：2020-01-24
Applicant: STMICROELECTRONICS S.r.l.
Inventor： Arcangelo Ranieri BRUNA , Danilo Pietro PAU
Abstract: An image processing system has one or more memories and image processing circuitry coupled to the one or more memories. The image processing circuitry, in operation, compares a first image to feature data in a comparison image space using a matching model. The comparing includes: unwarping keypoints in keypoint data of the first image; and comparing the unwarped keypoints and descriptor data associated with the first image to the feature data of the comparison image. The image processing circuitry determines whether the first image matches the comparison image based on the comparing.
-
公开(公告)号：US20190147338A1
公开(公告)日：2019-05-16
申请号：US16189264
申请日：2018-11-13
Applicant: STMICROELECTRONICS S.r.l.
Inventor： Danilo Pietro PAU , Emanuele PLEBANI , Fabio Giuseppe DE AMBROGGI , Floriana GUIDO , Angelo BOSCO
Abstract: A neural network classifies an input signal. For example, an accelerometer signal may be classified to detect human activity. In a first convolutional layer, two-valued weights are applied to the input signal. In a first two-valued function layer coupled at input to an output of the first convolutional layer, a two-valued function is applied. In a second convolutional layer coupled at input to an output of the first two-valued functional layer, weights of the second convolutional layer are applied. In a fully-connected layer coupled at input to an output of the second convolutional layer, two-valued weights of the fully connected layer are applied. In a second two-valued function layer coupled at input to an output of the fully connected layer, a two-valued function of the second two-valued function layer is applied. A classifier classifies the input signal based on an output signal of second two-valued function layer.
-
公开(公告)号：US20130216097A1
公开(公告)日：2013-08-22
申请号：US13773847
申请日：2013-02-22
Applicant: STMicroelectronics S.r.l.
Inventor： Danilo Pietro PAU , Arcangelo Ranieri BRUNA
IPC: G06K9/46
CPC classification number: G06K9/4642 , G06K9/4671 , G06T2207/20021
Abstract: An embodiment is a method for detecting image features, the method including extracting a stripe from a digital image, the stripe including of a plurality of blocks; processing the plurality of blocks for localizing one or more keypoints; and detecting one or more image features based on the one or more localized keypoints.
Abstract translation: 一个实施例是一种用于检测图像特征的方法，该方法包括从数字图像提取条带，包括多个块的条带; 处理多个块以用于定位一个或多个关键点; 以及基于所述一个或多个本地化关键点检测一个或多个图像特征。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.013 seconds)
